Admin: misc improvements on admin server and workers. EC now works. (#7055)
* initial design * added simulation as tests * reorganized the codebase to move the simulation framework and tests into their own dedicated package * integration test. ec worker task * remove "enhanced" reference * start master, volume servers, filer Current Status ✅ Master: Healthy and running (port 9333) ✅ Filer: Healthy and running (port 8888) ✅ Volume Servers: All 6 servers running (ports 8080-8085) 🔄 Admin/Workers: Will start when dependencies are ready * generate write load * tasks are assigned * admin start wtih grpc port. worker has its own working directory * Update .gitignore * working worker and admin. Task detection is not working yet. * compiles, detection uses volumeSizeLimitMB from master * compiles * worker retries connecting to admin * build and restart * rendering pending tasks * skip task ID column * sticky worker id * test canScheduleTaskNow * worker reconnect to admin * clean up logs * worker register itself first * worker can run ec work and report status but: 1. one volume should not be repeatedly worked on. 2. ec shards needs to be distributed and source data should be deleted. * move ec task logic * listing ec shards * local copy, ec. Need to distribute. * ec is mostly working now * distribution of ec shards needs improvement * need configuration to enable ec * show ec volumes * interval field UI component * rename * integration test with vauuming * garbage percentage threshold * fix warning * display ec shard sizes * fix ec volumes list * Update ui.go * show default values * ensure correct default value * MaintenanceConfig use ConfigField * use schema defined defaults * config * reduce duplication * refactor to use BaseUIProvider * each task register its schema * checkECEncodingCandidate use ecDetector * use vacuumDetector * use volumeSizeLimitMB * remove remove * remove unused * refactor * use new framework * remove v2 reference * refactor * left menu can scroll now * The maintenance manager was not being initialized when no data directory was configured for persistent storage. * saving config * Update task_config_schema_templ.go * enable/disable tasks * protobuf encoded task configurations * fix system settings * use ui component * remove logs * interface{} Reduction * reduce interface{} * reduce interface{} * avoid from/to map * reduce interface{} * refactor * keep it DRY * added logging * debug messages * debug level * debug * show the log caller line * use configured task policy * log level * handle admin heartbeat response * Update worker.go * fix EC rack and dc count * Report task status to admin server * fix task logging, simplify interface checking, use erasure_coding constants * factor in empty volume server during task planning * volume.list adds disk id * track disk id also * fix locking scheduled and manual scanning * add active topology * simplify task detector * ec task completed, but shards are not showing up * implement ec in ec_typed.go * adjust log level * dedup * implementing ec copying shards and only ecx files * use disk id when distributing ec shards 🎯 Planning: ActiveTopology creates DestinationPlan with specific TargetDisk 📦 Task Creation: maintenance_integration.go creates ECDestination with DiskId 🚀 Task Execution: EC task passes DiskId in VolumeEcShardsCopyRequest 💾 Volume Server: Receives disk_id and stores shards on specific disk (vs.store.Locations[req.DiskId]) 📂 File System: EC shards and metadata land in the exact disk directory planned * Delete original volume from all locations * clean up existing shard locations * local encoding and distributing * Update docker/admin_integration/EC-TESTING-README.md Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com> * check volume id range * simplify * fix tests * fix types * clean up logs and tests --------- Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>
This commit is contained in:
Chris Lu
@@ -1,60 +1,184 @@
|
||||
package vacuum
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"io"
|
||||
"time"
|
||||
|
||||
"github.com/seaweedfs/seaweedfs/weed/glog"
|
||||
"github.com/seaweedfs/seaweedfs/weed/pb"
|
||||
"github.com/seaweedfs/seaweedfs/weed/pb/volume_server_pb"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/tasks"
|
||||
"github.com/seaweedfs/seaweedfs/weed/worker/types"
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
)
|
||||
|
||||
// Task implements vacuum operation to reclaim disk space
|
||||
type Task struct {
|
||||
*tasks.BaseTask
|
||||
server string
|
||||
volumeID uint32
|
||||
server string
|
||||
volumeID uint32
|
||||
garbageThreshold float64
|
||||
}
|
||||
|
||||
// NewTask creates a new vacuum task instance
|
||||
func NewTask(server string, volumeID uint32) *Task {
|
||||
task := &Task{
|
||||
BaseTask: tasks.NewBaseTask(types.TaskTypeVacuum),
|
||||
server: server,
|
||||
volumeID: volumeID,
|
||||
BaseTask: tasks.NewBaseTask(types.TaskTypeVacuum),
|
||||
server: server,
|
||||
volumeID: volumeID,
|
||||
garbageThreshold: 0.3, // Default 30% threshold
|
||||
}
|
||||
return task
|
||||
}
|
||||
|
||||
// Execute executes the vacuum task
|
||||
// Execute performs the vacuum operation
|
||||
func (t *Task) Execute(params types.TaskParams) error {
|
||||
glog.Infof("Starting vacuum task for volume %d on server %s", t.volumeID, t.server)
|
||||
// Use BaseTask.ExecuteTask to handle logging initialization
|
||||
return t.ExecuteTask(context.Background(), params, t.executeImpl)
|
||||
}
|
||||
|
||||
// Simulate vacuum operation with progress updates
|
||||
steps := []struct {
|
||||
name string
|
||||
duration time.Duration
|
||||
progress float64
|
||||
}{
|
||||
{"Scanning volume", 1 * time.Second, 20},
|
||||
{"Identifying deleted files", 2 * time.Second, 50},
|
||||
{"Compacting data", 3 * time.Second, 80},
|
||||
{"Finalizing vacuum", 1 * time.Second, 100},
|
||||
// executeImpl is the actual vacuum implementation
|
||||
func (t *Task) executeImpl(ctx context.Context, params types.TaskParams) error {
|
||||
t.LogInfo("Starting vacuum for volume %d on server %s", t.volumeID, t.server)
|
||||
|
||||
// Parse garbage threshold from typed parameters
|
||||
if params.TypedParams != nil {
|
||||
if vacuumParams := params.TypedParams.GetVacuumParams(); vacuumParams != nil {
|
||||
t.garbageThreshold = vacuumParams.GarbageThreshold
|
||||
t.LogWithFields("INFO", "Using garbage threshold from parameters", map[string]interface{}{
|
||||
"threshold": t.garbageThreshold,
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
for _, step := range steps {
|
||||
if t.IsCancelled() {
|
||||
return fmt.Errorf("vacuum task cancelled")
|
||||
// Convert server address to gRPC address and use proper dial option
|
||||
grpcAddress := pb.ServerToGrpcAddress(t.server)
|
||||
var dialOpt grpc.DialOption = grpc.WithTransportCredentials(insecure.NewCredentials())
|
||||
if params.GrpcDialOption != nil {
|
||||
dialOpt = params.GrpcDialOption
|
||||
}
|
||||
|
||||
conn, err := grpc.NewClient(grpcAddress, dialOpt)
|
||||
if err != nil {
|
||||
t.LogError("Failed to connect to volume server %s: %v", t.server, err)
|
||||
return fmt.Errorf("failed to connect to volume server %s: %v", t.server, err)
|
||||
}
|
||||
defer conn.Close()
|
||||
|
||||
client := volume_server_pb.NewVolumeServerClient(conn)
|
||||
|
||||
// Step 1: Check vacuum eligibility
|
||||
t.SetProgress(10.0)
|
||||
t.LogDebug("Checking vacuum eligibility for volume %d", t.volumeID)
|
||||
|
||||
checkResp, err := client.VacuumVolumeCheck(ctx, &volume_server_pb.VacuumVolumeCheckRequest{
|
||||
VolumeId: t.volumeID,
|
||||
})
|
||||
if err != nil {
|
||||
t.LogError("Vacuum check failed for volume %d: %v", t.volumeID, err)
|
||||
return fmt.Errorf("vacuum check failed for volume %d: %v", t.volumeID, err)
|
||||
}
|
||||
|
||||
// Check if garbage ratio meets threshold
|
||||
if checkResp.GarbageRatio < t.garbageThreshold {
|
||||
t.LogWarning("Volume %d garbage ratio %.2f%% is below threshold %.2f%%, skipping vacuum",
|
||||
t.volumeID, checkResp.GarbageRatio*100, t.garbageThreshold*100)
|
||||
return fmt.Errorf("volume %d garbage ratio %.2f%% is below threshold %.2f%%, skipping vacuum",
|
||||
t.volumeID, checkResp.GarbageRatio*100, t.garbageThreshold*100)
|
||||
}
|
||||
|
||||
t.LogWithFields("INFO", "Volume eligible for vacuum", map[string]interface{}{
|
||||
"volume_id": t.volumeID,
|
||||
"garbage_ratio": checkResp.GarbageRatio,
|
||||
"threshold": t.garbageThreshold,
|
||||
"garbage_percent": checkResp.GarbageRatio * 100,
|
||||
})
|
||||
|
||||
// Step 2: Compact volume
|
||||
t.SetProgress(30.0)
|
||||
t.LogInfo("Starting compact for volume %d", t.volumeID)
|
||||
|
||||
compactStream, err := client.VacuumVolumeCompact(ctx, &volume_server_pb.VacuumVolumeCompactRequest{
|
||||
VolumeId: t.volumeID,
|
||||
})
|
||||
if err != nil {
|
||||
t.LogError("Vacuum compact failed for volume %d: %v", t.volumeID, err)
|
||||
return fmt.Errorf("vacuum compact failed for volume %d: %v", t.volumeID, err)
|
||||
}
|
||||
|
||||
// Process compact stream and track progress
|
||||
var processedBytes int64
|
||||
var totalBytes int64
|
||||
|
||||
for {
|
||||
resp, err := compactStream.Recv()
|
||||
if err != nil {
|
||||
if err == io.EOF {
|
||||
break
|
||||
}
|
||||
t.LogError("Vacuum compact stream error for volume %d: %v", t.volumeID, err)
|
||||
return fmt.Errorf("vacuum compact stream error for volume %d: %v", t.volumeID, err)
|
||||
}
|
||||
|
||||
glog.V(1).Infof("Vacuum task step: %s", step.name)
|
||||
t.SetProgress(step.progress)
|
||||
processedBytes = resp.ProcessedBytes
|
||||
if resp.LoadAvg_1M > 0 {
|
||||
totalBytes = int64(resp.LoadAvg_1M) // This is a rough approximation
|
||||
}
|
||||
|
||||
// Simulate work
|
||||
time.Sleep(step.duration)
|
||||
// Update progress based on processed bytes (30% to 70% of total progress)
|
||||
if totalBytes > 0 {
|
||||
compactProgress := float64(processedBytes) / float64(totalBytes)
|
||||
if compactProgress > 1.0 {
|
||||
compactProgress = 1.0
|
||||
}
|
||||
progress := 30.0 + (compactProgress * 40.0) // 30% to 70%
|
||||
t.SetProgress(progress)
|
||||
}
|
||||
|
||||
t.LogWithFields("DEBUG", "Volume compact progress", map[string]interface{}{
|
||||
"volume_id": t.volumeID,
|
||||
"processed_bytes": processedBytes,
|
||||
"total_bytes": totalBytes,
|
||||
"compact_progress": fmt.Sprintf("%.1f%%", (float64(processedBytes)/float64(totalBytes))*100),
|
||||
})
|
||||
}
|
||||
|
||||
glog.Infof("Vacuum task completed for volume %d on server %s", t.volumeID, t.server)
|
||||
// Step 3: Commit vacuum changes
|
||||
t.SetProgress(80.0)
|
||||
t.LogInfo("Committing vacuum for volume %d", t.volumeID)
|
||||
|
||||
commitResp, err := client.VacuumVolumeCommit(ctx, &volume_server_pb.VacuumVolumeCommitRequest{
|
||||
VolumeId: t.volumeID,
|
||||
})
|
||||
if err != nil {
|
||||
t.LogError("Vacuum commit failed for volume %d: %v", t.volumeID, err)
|
||||
return fmt.Errorf("vacuum commit failed for volume %d: %v", t.volumeID, err)
|
||||
}
|
||||
|
||||
// Step 4: Cleanup temporary files
|
||||
t.SetProgress(90.0)
|
||||
t.LogInfo("Cleaning up vacuum files for volume %d", t.volumeID)
|
||||
|
||||
_, err = client.VacuumVolumeCleanup(ctx, &volume_server_pb.VacuumVolumeCleanupRequest{
|
||||
VolumeId: t.volumeID,
|
||||
})
|
||||
if err != nil {
|
||||
// Log warning but don't fail the task
|
||||
t.LogWarning("Vacuum cleanup warning for volume %d: %v", t.volumeID, err)
|
||||
}
|
||||
|
||||
t.SetProgress(100.0)
|
||||
|
||||
newVolumeSize := commitResp.VolumeSize
|
||||
t.LogWithFields("INFO", "Successfully completed vacuum", map[string]interface{}{
|
||||
"volume_id": t.volumeID,
|
||||
"server": t.server,
|
||||
"new_volume_size": newVolumeSize,
|
||||
"garbage_reclaimed": true,
|
||||
})
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -71,9 +195,20 @@ func (t *Task) Validate(params types.TaskParams) error {
|
||||
|
||||
// EstimateTime estimates the time needed for the task
|
||||
func (t *Task) EstimateTime(params types.TaskParams) time.Duration {
|
||||
// Base time for vacuum operation
|
||||
baseTime := 25 * time.Second
|
||||
// Base time for vacuum operations - varies by volume size and garbage ratio
|
||||
// Typically vacuum is faster than EC encoding
|
||||
baseTime := 5 * time.Minute
|
||||
|
||||
// Could adjust based on volume size or usage patterns
|
||||
// Use default estimation since volume size is not available in typed params
|
||||
return baseTime
|
||||
}
|
||||
|
||||
// GetProgress returns the current progress
|
||||
func (t *Task) GetProgress() float64 {
|
||||
return t.BaseTask.GetProgress()
|
||||
}
|
||||
|
||||
// Cancel cancels the task
|
||||
func (t *Task) Cancel() error {
|
||||
return t.BaseTask.Cancel()
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user